metadata
base_model: microsoft/resnet-101
library_name: transformers
pipeline_tag: image-classification
tags:
- probex
- model-j
- weight-space-learning
Model-J: ResNet Model (model_idx_0285)
This model is part of the Model-J dataset, introduced in:
Learning on Model Weights using Tree Experts (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
🌐 Project | 📃 Paper | 💻 GitHub | 🤗 Dataset
Model Details
| Attribute | Value |
|---|---|
| Subset | ResNet |
| Split | train |
| Base Model | microsoft/resnet-101 |
| Dataset | CIFAR100 (50 classes) |
Training Hyperparameters
| Parameter | Value |
|---|---|
| Learning Rate | 9e-05 |
| LR Scheduler | cosine |
| Epochs | 4 |
| Max Train Steps | 1332 |
| Batch Size | 64 |
| Weight Decay | 0.009 |
| Seed | 285 |
| Random Crop | False |
| Random Flip | True |
Performance
| Metric | Value |
|---|---|
| Train Accuracy | 0.9078 |
| Val Accuracy | 0.8749 |
| Test Accuracy | 0.8684 |
Training Categories
The model was fine-tuned on the following 50 CIFAR100 classes:
bicycle, trout, poppy, boy, bee, streetcar, can, orchid, caterpillar, bus, bridge, sunflower, cup, forest, wardrobe, turtle, chair, fox, shark, raccoon, dinosaur, road, wolf, cloud, mouse, table, kangaroo, tank, porcupine, ray, willow_tree, rocket, train, woman, butterfly, tulip, palm_tree, snake, spider, oak_tree, camel, whale, couch, pear, rabbit, apple, house, sea, motorcycle, tractor